爬取漫画 python 爬取漫画爬虫软件

爬取”漫画岛“《鬼抬轿》

# 导入第三方库
import requests
from bs4 import BeautifulSoup
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 \
    Safari/537.36'
}

# 获取请求，获取网页源代码
def open_url(url):
    r = requests.get(url, headers=headers)
    return r.text

# 获得各个图片链接并保存
def save_img(contents):
    u = []
    soup = BeautifulSoup(contents, 'lxml')
    img_urls = soup.find_all('li', style="margin-bottom:0")
    name_num = 1
    for img_url in img_urls:
        ul = img_url.img.get('src')
        rs = requests.get(ul).content
        # 保存图片到本地
        with open('《鬼抬轿》第一话第{}页'.format(name_num) + '.jpg', 'wb') as e:   # 'wb'以二进制文件写入
            e.write(rs)
        print('漫画《鬼抬轿》第一话第{}页已经下载完成！'.format(name_num))
        name_num += 1

# 主程序
def main():
    url = 'http://www.manhuadao.cn/Comic/ComicView?comicid=58ddaeb027a7c1392c224ce5'
    response = open_url(url)
    save_img(response)

# 执行程序
if __name__ == '__main__':
    main()